Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Player of Games

arxiv.org

Post reply on HN
Print view View original

51–60 of 242 posts

Re: Player of Games

#51

Post by stavros »

WJW wrote: post #47
macmac wrote: post #41

Earlier quoted context omitted.

At least that is what the ship (SC) wants him to think.

Indeed. (spoiler following) The plot basically revolves around SC manipulating both Gurgeh and the Empire of Azad in an ever bigger and complex game than the one in the book. Given how Banks describes the Minds in other books it would be extremely curious if they wouldn't crush any biological player in any normal game the same way chess computers crush humans these days. But, it is possible that a more limited mind l…

How did I miss this plot point? It's been a while, but I remember focusing on the game Gurgeh played. Maybe I just don't remember it now.

Re: Player of Games

#53

Post by robbie-c »

moritonal wrote: post #49
CobrastanJorji wrote: post #18

Earlier quoted context omitted.

Allusions are fun and all, but I disagree. These are important problems that a lot of people have put their whole careers into researching. Silly names like these lack gravitas.

Sorry, to explain the joke. The ships name themselves, and when they pick jokey names they're often mocked by the humans (which are in every way essentially ants to the spaceships) for not having enough gravitas. So the ships start naming themeselves things like the "Death-ray 9000 super-killer deluxe", to essentially take the piss. Funnily enough you can see the exact same effect in principal game-engineers or compu…

I believe the user you are replying to was also joking, given that many of Banks' ship names reference the g-word

Edit: if not that's even more amusing

Re: Player of Games

#54

Post by fxtentacle »

sillysaurusx wrote: post #40
fxtentacle wrote: post #39

This is a great result, but you can see that it's more of a theoretical case because of this: "converging to perfect play as available computation time and approximation capacity increases." That is true for pretty much all current deep reinforcement learning algorithms. The practical question is: How much computation do you need to get useful results? Alpha Go Zero is impressive mathematics, but who is willing to sp…

You often don't need anywhere near the amount of compute in these papers to get similar performance. Suppose you're a business that needs to play games. Most people seem to think that it's a matter of plugging in the settings from the paper, buying the same hardware, then clicking a button and waiting. It's not. The specific settings matter a lot. But my main point is that you'll get most of your performance pretty r…

My personal experience was the opposite. I'm currently trying different approaches for building a Bomberman AI for the Bomberland competition that was discussed here on HN a few weeks ago.

"IMPALA with 1 learner takes only around 10 hours to reach the same performance that A3C approaches after 7.5 days." says the paper, but I can run A3C on a cheap CPU-only server but to get that IMPALA timing, I need to spend a lot of money. But my biggest roadblock so far is that I need compute far exceeding what the papers claim.

The diagrams for IMPALA show good performance starting at 1e8 environment frames and excellent performance at 1e9 frames. By now, I'm at 2.5e9 frames and performance is still bad. In my opinion, the reason is that the sequence lengths for Bomberland are quite long. To clear a path, you place a bomb, wait 5 ticks for it to become detonatable, then detonate it, then wait 10 ticks for the fire to clear. With 7 possible actions per tick, the chance of randomly executing this 17 tick sequence becomes (1/7)^17 = 4e-15. If I calculate optimistically that all moves are valid, too, while we wait, then I can get up to (1/7)(5/7)^5(1/7)*(5/7)^10 = 1e-4. But that still means that at 1e8 env steps, I only have 1000 successful executions to learn from.

Re: Player of Games

#55

Post by nicolodavis »

fho wrote: post #43
captn3m0 wrote: post #7

If you are interested in this, I maintain a list of boardgame-solving related research at https://github.com/captn3m0/boardgame-research , with sections for specific games. This looks really interesting. It would be a good project to test this against a general card-playing framework to easily test it on a variety of imperfect-information games based on playing cards.

I tried my hand once or twice at (re-)implementing board games [0], so that I could run some common "AI" algorithms on the game trees. What tripped me up every time is that most board games have a lot of "if this happens, there is this specific rule that applies". Even relatively simple games (like Homeworlds) are pretty hard to nail down perfectly due to all the special cases. Do you, or somebody else, have any reco…

You could consider using a library like boardgame.io for this.

Re: Player of Games

#57

Post by automatic6131 »

7thaccount wrote: post #12
sdenton4 wrote: post #3

This is clearly part of DeepMind's long-game plan to achieve world domination through board game mastery. Naming the new algorithm after the book is a real tip of their hand... https://en.wikipedia.org/wiki/The_Player_of_Games

Pretty amazing book. I wish I could play a board game like that as well.

I always imagine the board game as essentially being SM's Civilisation but really, really good in an indescribable way - with some card games inbetween.

Re: Player of Games

#58

Post by jart »

wetpaws wrote: post #17
wly_cdgr wrote: post #14

The future is so depressing

Fun fact: The consensus between professional go and chess players is that all new AI systems (alphago, etc) have really revitalised the game and introduced incredible amount of new strategies and depth.

Sad fact: Lee Sedol retired after AlphaGo defeated him.

Re: Player of Games

#59

Post by captn3m0 »

fho wrote: post #43
captn3m0 wrote: post #7

If you are interested in this, I maintain a list of boardgame-solving related research at https://github.com/captn3m0/boardgame-research , with sections for specific games. This looks really interesting. It would be a good project to test this against a general card-playing framework to easily test it on a variety of imperfect-information games based on playing cards.

I tried my hand once or twice at (re-)implementing board games [0], so that I could run some common "AI" algorithms on the game trees. What tripped me up every time is that most board games have a lot of "if this happens, there is this specific rule that applies". Even relatively simple games (like Homeworlds) are pretty hard to nail down perfectly due to all the special cases. Do you, or somebody else, have any reco…

+1 to boardgame.io. It provides very good abstractions for turns, phases, players, and partial information. I’ve implemented small games with a few hours of effort, and that includes a UI.
Post reply on HN